pay_send

Send a one-shot USDC payment to an address. Use this for single transfers,

SERVERPay Mcp SOURCE@pay-skill/mcp

Critical RISK CLASS

Category Financial

Parameters 00 required

Recommended Approval-gatedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-pay-skill-pay-mcp/pay-send.md

WHAT IT DOES

What pay_send does on Pay Mcp

AI agents use pay_send to commit financial operations through Pay Mcp, usually the final step of a payment, billing, or trading workflow. A call moves real money.

RISK

Why pay_send is rated Critical

This tool directly moves money (USDC tokens) from one account to another based on agent-provided arguments (recipient address and amount). Even a single misdirected or maliciously-crafted payment could result in irreversible loss of funds. This is the highest-severity category due to direct financial impact and potential for substantial monetary harm.

From the tool's definition Tool name 'pay_send' and description 'Send a one-shot USDC payment to an address. Use this for single transfers' explicitly indicates direct transfer of USDC (a stablecoin) to a specified recipient.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs pay_send safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Pay Mcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For pay_send, this is the rule to start with:

pay_send Approval-gated

Any call to pay_send is blocked until a human approves it. The rest of the server keeps working.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "pay_send": {
      "deny_if": [
        {
          "conditions": [],
          "on_deny": "Requires human approval."
        }
      ]
    }
  }
}

GATE THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Pay Mcp, apply this rule, and every pay_send call is checked against it from then on.

FAQ

Questions about pay_send

What does the pay_send tool do? +

Send a one-shot USDC payment to an address. Use this for single transfers,. It is categorised as a Financial tool in the Pay Mcp MCP Server, which means it involves financial transactions. Block by default and require explicit approval.

How do I enforce a policy on pay_send? +

Register the Pay MCP server in PolicyLayer and add a rule for pay_send: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Pay Mcp. Nothing to install.

What risk level is pay_send? +

pay_send is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit pay_send? +

Yes. Add a rate_limit block to the pay_send rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block pay_send completely? +

Set action: deny in the PolicyLayer policy for pay_send. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides pay_send? +

pay_send is provided by the Pay MCP server (@pay-skill/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Pay, and thousands of servers like it.

This server

All 15 Pay tools → Critical-risk tools on this server →

Across the catalogue

pay_invoice on Bitcoin MCP Server →menese_send on Mcp Menesesdk → All critical-risk MCP tools → The MCP Attack Database →

Guides

Govern MCP payment tools →Human-in-the-loop →Tool call approval →